userfaultfd: non-cooperative: add event for memory unmaps

When a non-cooperative userfaultfd monitor copies pages in the
background, it may encounter regions that were already unmapped.
Addition of UFFD_EVENT_UNMAP allows the uffd monitor to track precisely
changes in the virtual memory layout.

Since there might be different uffd contexts for the affected VMAs, we
first should create a temporary representation for the unmap event for
each uffd context and then notify them one by one to the appropriate
userfault file descriptors.

The event notification occurs after the mmap_sem has been released.

[arnd@arndb.de: fix nommu build]
  Link: http://lkml.kernel.org/r/20170203165141.3665284-1-arnd@arndb.de
[mhocko@suse.com: fix nommu build]
  Link: http://lkml.kernel.org/r/20170202091503.GA22823@dhcp22.suse.cz
Link: http://lkml.kernel.org/r/1485542673-24387-3-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 14 insertions, 9 deletions

diff --git a/mm/mremap.c b/mm/mremap.c
index 8779928d6a70..8233b0105c82 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -252,7 +252,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 static unsigned long move_vma(struct vm_area_struct *vma,
 		unsigned long old_addr, unsigned long old_len,
 		unsigned long new_len, unsigned long new_addr,
-		bool *locked, struct vm_userfaultfd_ctx *uf)
+		bool *locked, struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *new_vma;
@@ -341,7 +342,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
 		untrack_pfn_moved(vma);
 
-	if (do_munmap(mm, old_addr, old_len) < 0) {
+	if (do_munmap(mm, old_addr, old_len, uf_unmap) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		vm_unacct_memory(excess >> PAGE_SHIFT);
 		excess = 0;
@@ -417,7 +418,8 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr,
 
 static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 		unsigned long new_addr, unsigned long new_len, bool *locked,
-		struct vm_userfaultfd_ctx *uf)
+		struct vm_userfaultfd_ctx *uf,
+		struct list_head *uf_unmap)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
@@ -435,12 +437,12 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (addr + old_len > new_addr && new_addr + new_len > addr)
 		goto out;
 
-	ret = do_munmap(mm, new_addr, new_len);
+	ret = do_munmap(mm, new_addr, new_len, NULL);
 	if (ret)
 		goto out;
 
 	if (old_len >= new_len) {
-		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		ret = do_munmap(mm, addr+new_len, old_len - new_len, uf_unmap);
 		if (ret && old_len != new_len)
 			goto out;
 		old_len = new_len;
@@ -462,7 +464,8 @@ static unsigned long mremap_to(unsigned long addr, unsigned long old_len,
 	if (offset_in_page(ret))
 		goto out1;
 
-	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf);
+	ret = move_vma(vma, addr, old_len, new_len, new_addr, locked, uf,
+		       uf_unmap);
 	if (!(offset_in_page(ret)))
 		goto out;
 out1:
@@ -502,6 +505,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	unsigned long charged = 0;
 	bool locked = false;
 	struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX;
+	LIST_HEAD(uf_unmap);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
@@ -528,7 +532,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 
 	if (flags & MREMAP_FIXED) {
 		ret = mremap_to(addr, old_len, new_addr, new_len,
-				&locked, &uf);
+				&locked, &uf, &uf_unmap);
 		goto out;
 	}
 
@@ -538,7 +542,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	 * do_munmap does all the needed commit accounting
 	 */
 	if (old_len >= new_len) {
-		ret = do_munmap(mm, addr+new_len, old_len - new_len);
+		ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap);
 		if (ret && old_len != new_len)
 			goto out;
 		ret = addr;
@@ -598,7 +602,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 		}
 
 		ret = move_vma(vma, addr, old_len, new_len, new_addr,
-			       &locked, &uf);
+			       &locked, &uf, &uf_unmap);
 	}
 out:
 	if (offset_in_page(ret)) {
@@ -609,5 +613,6 @@ out:
 	if (locked && new_len > old_len)
 		mm_populate(new_addr + old_len, new_len - old_len);
 	mremap_userfaultfd_complete(&uf, addr, new_addr, old_len);
+	userfaultfd_unmap_complete(mm, &uf_unmap);
 	return ret;
 }